Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “,
    -0.07
    *f
    -0.07
    ^n
    -0.07
     ",
    -0.07
    ",
    -0.06
    .Dataset
    -0.06
    getSource
    -0.06
    -dark
    -0.06
    *z
    -0.06
    *y
    -0.06
    POSITIVE LOGITS
     Sherlock
    0.08
     link
    0.07
    станов
    0.07
     Commerce
    0.07
     encourage
    0.07
    ्यक
    0.07
     asia
    0.06
     rek
    0.06
    arranty
    0.06
    icipant
    0.06
    Act Density 0.003%

    No Known Activations